© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 39211
    Prev
    Next
    INDEX
    Explanations

    references to optimization processes and algorithms in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ³ãĥĸ
    -0.07
    ige
    -0.06
    yp
    -0.06
    accent
    -0.06
    UBE
    -0.06
    anda
    -0.06
    alo
    -0.06
    ada
    -0.06
    ä¹
    -0.06
    resp
    -0.06
    POSITIVE LOGITS
     discussed
    0.18
     see
    0.16
     below
    0.15
     See
    0.14
    see
    0.14
    disc
    0.13
    See
    0.13
     discuss
    0.13
     later
    0.12
    below
    0.12
    Activations Density 0.200%

    No Known Activations